Each year in Europe, more than 300,000 newborns are born prematurely. Among them, very premature babies have a 10-20% risk of contracting late neonatal infections, with a high risk of mortality or neurobehavioural sequelae. However, the ability to quickly and accurately diagnose the risk of infection in premature newborns based on clinical assessment and laboratory blood tests remains a challenge. In a personalized and precision medicine approach, the proposed project aims to validate and deploy a new non-invasive medical decision support system for early diagnosis of infection in premature newborns. It aims to prepare a proposal for the call H2020 SC1-BHC-06-2020: Digital diagnostics - developing tools for supporting clinical decisions by integrating various diagnostic data from WP2020. Digi-Sepsis uses artificial intelligence methods to detect early infections. It builds on the experience and major progress made in the previous H2020 Digi-NewB project (www.digi-newb.eu) which ends in February 2020. This project resulted in the development of a proof of concept based on a multi-source database of more than 400 patients, an interface validated by ergonomic experts with the nursing staff, a validated and operational architecture for a randomized study, by carrying out a first phase of tests in hospital/neonatology with monitoring of the risk of sepsis. This approach aims to reduce morbidity and mortality associated with late neonatal infections. It requires continuous, real-time measurement of a set of clinical (medical record) and physiological (signal processing) variables and their association with recent and developing biological tools ("-omic", immunological biomarkers and PCR). The Digi-Sepsis project aims to meet the following specific objectives: The issues that will be addressed in the present study are: (i) To propose a definition of the early phase of sepsis which is necessary to evaluate the accuracy and predictive value of the proposed approach. (ii) To evaluate the accuracy of the proposed multi-dimensional approach in terms of sensitivity, specificity, predictive values and significance for the clinicians (iii) To demonstrate a benefice for the patients in the use of AI for the early diagnosis of infection before the occurrence of established sepsis, (iv) To evaluate the perception of the proposed approach by patients, parents and health care givers. In the long term, it is expected that new therapeutic strategies will be developed that combine early treatment with a reduction in the inappropriate use of antibiotics.